ICLR

Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Yuan-Hong Liao, Joshua B. Tenenbaum, Sanja Fidler, Antonio Torralba

Comments ICLR 2021

Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell

Comments Accepted at ICLR 2021

Robust and Generalizable Visual Representation Learning via Random Convolutions

Zhenlin Xu, Deyi Liu, Junlin Yang, Colin Raffel, Marc Niethammer

Comments ICLR 2021. Code is available at https://github.com/wildphoton/RandConv

A Good Image Generator Is What You Need for High-Resolution Video Synthesis

Yu Tian, Jian Ren, Menglei Chai, Kyle Olszewski, Xi Peng, Dimitris N. Metaxas, Sergey Tulyakov

Comments Accepted to ICLR 2021

Active WeaSuL: Improving Weak Supervision with Active Learning

Samantha Biegel, Rafah El-Khatib, Luiz Otavio Vilas Boas Oliveira, Max Baak, Nanne Aben

Comments Accepted to the ICLR 2021 Workshop on Weakly Supervised Learning

Studying the Consistency and Composability of Lottery Ticket Pruning Masks

Rajiv Movva, Jonathan Frankle, Michael Carbin

Comments Workshop on Science and Engineering of Deep Learning (ICLR 2021)

What is Going on Inside Recurrent Meta Reinforcement Learning Agents?

Safa Alver, Doina Precup

Comments Accepted to the Never-Ending Reinforcement Learning Workshop at ICLR 2021

Improving Simulations with Symmetry Control Neural Networks

Marc Syvaeri, Sven Krippendorf

Comments 7 pages, 2 figures, accepted as workshop paper at ICLR 2021 SimDL Workshop

A neural anisotropic view of underspecification in deep learning

Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Comments Presented as a RobustML workshop paper at ICLR 2021

Meta-learning using privileged information for dynamics

Ben Day, Alexander Norcliffe, Jacob Moss, Pietro Liò

Comments Published as a workshop paper at the Learning to Learn and SimDL workshops at ICLR 2021. 4 pages, 3 pages of appendices

Adapting to Reward Progressivity via Spectral Reinforcement Learning

Michael Dann, John Thangarajah

Comments 16 pages, 8 figures, 3 tables, accepted as a conference paper at ICLR 2021

Analyzing the Nuances of Transformers' Polynomial Simplification Abilities

Vishesh Agarwal, Somak Aditya, Navin Goyal

Comments 16 pages, 18 Tables, Accepted ICLR 2021 MathAI Workshop

On the advantages of stochastic encoders

Lucas Theis, Eirikur Agustsson

Journal ref ICLR 2021 Neural Compression Workshop

Optimal Regularization Can Mitigate Double Descent

Preetum Nakkiran, Prayaag Venkat, Sham Kakade, Tengyu Ma

Comments v2: Accepted to ICLR 2021. Minor edits to Intro and Appendix

Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization

Michael R. Zhang, Tom Le Paine, Ofir Nachum, Cosmin Paduraru, George Tucker, Ziyu Wang, Mohammad Norouzi

Comments ICLR 2021. 17 pages

A coding theorem for the rate-distortion-perception function

Lucas Theis, Aaron B. Wagner

Journal ref ICLR 2021 Neural Compression Workshop

The Role of General Intelligence in Mathematical Reasoning

Aviv Keren

Journal ref 1st Mathematical Reasoning in General Artificial Intelligence Workshop, ICLR 2021

Conditional Coding for Flexible Learned Video Compression

Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges

Comments Neural Compression Workshop @ ICLR 2021

TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption

Ayoub Benaissa, Bilal Retiat, Bogdan Cebere, Alaa Eddine Belfedhal

Comments ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)

Towards Robust Neural Networks via Close-loop Control

Zhuotong Chen, Qianxiao Li, Zheng Zhang

Comments Published as a conference paper at ICLR 2021

Large Associative Memory Problem in Neurobiology and Machine Learning

Dmitry Krotov, John Hopfield

Comments Accepted for publication at ICLR 2021

Width Transfer: On the (In)variance of Width Optimization

Ting-Wu Chin, Diana Marculescu, Ari S. Morcos

Comments Full paper accepted at CVPR Workshops 2021; a 4-page abridged version is accepted at ICLR 2021 NAS Workshop

Handling Long-Tail Queries with Slice-Aware Conversational Systems

Cheng Wang, Sun Kim, Taiwoo Park, Sajal Choudhary, Sunghyun Park, Young-Bum Kim, Ruhi Sarikaya, Sungjin Lee

Comments Published at ICLR 2021 Workshop on Weakly Supervised Learning

Online parameter inference for the simulation of a Bunsen flame using heteroscedastic Bayesian neural network ensembles

Maximilian L. Croci, Ushnish Sengupta, Matthew P. Juniper

Comments 6 pages, 3 figures

Journal ref ICLR 2021 Deep Learning for Simulation Workshop

CosmicRIM : Reconstructing Early Universe by Combining Differentiable Simulations with Recurrent Inference Machines

Chirag Modi, François Lanusse, Uroš Seljak, David N. Spergel, Laurence Perreault-Levasseur

Comments Published as a workshop paper at ICLR 2021 SimDL Workshop

Syft 0.5: A Platform for Universally Deployable Structured Transparency

Adam James Hall, Madhava Jay, Tudor Cebere, Bogdan Cebere, Koen Lennart van der Veen, George Muraru, Tongye Xu, Patrick Cason, William Abramson, Ayoub Benaissa, Chinmay Shah, Alan Aboudib, Théo Ryffel, Kritika Prakash, Tom Titcombe, Varun Kumar Khare, Maddie Shang, Ionesio Junior, Animesh Gupta, Jason Paumier, Nahua Kang, Vova Manannikov, Andrew Trask

Comments ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)

Persistent Message Passing

Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Veličković

Comments 7 pages, 2 figures. Published as a workshop paper at ICLR 2021 SimDL Workshop. Accepted at the ICLR 2021 Workshop on Geometrical and Topological Representation Learning

A statistical theory of cold posteriors in deep neural networks

Laurence Aitchison

Comments Published at ICLR 2021 (https://openreview.net/forum?id=Rd138pWXMvG)

Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training

Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, Vera Demberg

Comments Accepted to Workshop at ICLR 2020

Towards Sustainable Census Independent Population Estimation in Mozambique

Isaac Neal, Sohan Seth, Gary Watmough, Mamadou Saliou Diallo

Comments 5 pages, 2 figures, published in the AI for Public Health Workshop, ICLR 2021